簡化的網絡模型
###########————————————————————導包————————————————————————————————############## import numpy as np import pandas as pd import matplotlib.pyplot as plt import torch import torch.optim as optim import warnings warnings.filterwarnings("ignore") # 將python中產生的warning信息忽略 %matplotlib inline ##---------------傳數據------------------ features = pd.read_csv('temps.csv') # 處理時間數據 import datetime # 分別得到年,月,日 years = features['year'] months = features['month'] days = features['day'] # datetime格式 dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)] dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates] #----------------------- 准備畫圖------------------------ # 指定默認風格 plt.style.use('fivethirtyeight') # 設置布局 fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize = (10,10)) fig.autofmt_xdate(rotation = 45) # 標簽值 ax1.plot(dates, features['actual']) ax1.set_xlabel(''); ax1.set_ylabel('Temperature'); ax1.set_title('Max Temp') # 昨天 ax2.plot(dates, features['temp_1']) ax2.set_xlabel(''); ax2.set_ylabel('Temperature'); ax2.set_title('Previous Max Temp') # 前天 ax3.plot(dates, features['temp_2']) ax3.set_xlabel('Date'); ax3.set_ylabel('Temperature'); ax3.set_title('Two Days Prior Max Temp') # 我的逗逼朋友 ax4.plot(dates, features['friend']) ax4.set_xlabel('Date'); ax4.set_ylabel('Temperature'); ax4.set_title('Friend Estimate') plt.tight_layout(pad=2) #數據格式化 獨熱編碼 features = pd.get_dummies(features) features.head(5) # 標簽 labels = np.array(features['actual']) # 在特征中去掉標簽 features= features.drop('actual', axis = 1) # 名字單獨保存一下,以備后患 feature_list = list(features.columns) # 轉換成合適的格式 features = np.array(features) #數據預處理 from sklearn import preprocessing input_features = preprocessing.StandardScaler().fit_transform(features) ##############——————————————————————————————搭建pytorch————————————————————########## input_size = input_features.shape[1] hidden_size = 128 output_size = 1 batch_size = 16 my_nn = torch.nn.Sequential( # 類似keras torch.nn.Linear(input_size, hidden_size), torch.nn.Sigmoid(), torch.nn.Linear(hidden_size, output_size), ) cost = torch.nn.MSELoss(reduction='mean') optimizer = torch.optim.Adam(my_nn.parameters(), lr = 0.001) # 訓練網絡 losses = [] for i in range(1000): batch_loss = [] # MINI-Batch方法來進行訓練 for start in range(0, len(input_features), batch_size): end = start + batch_size if start + batch_size < len(input_features) else len(input_features) xx = torch.tensor(input_features[start:end], dtype = torch.float, requires_grad = True) yy = torch.tensor(labels[start:end], dtype = torch.float, requires_grad = True) prediction = my_nn(xx) loss = cost(prediction, yy) optimizer.zero_grad() loss.backward(retain_graph=True) optimizer.step() batch_loss.append(loss.data.numpy()) # 打印損失 if i % 100==0: losses.append(np.mean(batch_loss)) print(i, np.mean(batch_loss)) ##測試 x = torch.tensor(input_features, dtype = torch.float) predict = my_nn(x).data.numpy() # 轉換日期格式 dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)] dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates] # 創建一個表格來存日期和其對應的標簽數值 true_data = pd.DataFrame(data = {'date': dates, 'actual': labels}) # 同理,再創建一個來存日期和其對應的模型預測值 months = features[:, feature_list.index('month')] days = features[:, feature_list.index('day')] years = features[:, feature_list.index('year')] test_dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)] test_dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in test_dates] predictions_data = pd.DataFrame(data = {'date': test_dates, 'prediction': predict.reshape(-1)}) # 真實值 plt.plot(true_data['date'], true_data['actual'], 'b-', label = 'actual') # 預測值 plt.plot(predictions_data['date'], predictions_data['prediction'], 'ro', label = 'prediction') plt.xticks(rotation = '60'); plt.legend() # 圖名 plt.xlabel('Date'); plt.ylabel('Maximum Temperature (F)'); plt.title('Actual and Predicted Values');
復雜的網絡模型
import pandas as pd import numpy as np import datetime import matplotlib.pyplot as plt features = pd.read_csv('temps.csv') # 可視化圖形 print(features.head(5)) #使用日期構造可視化圖像 dates = [str(int(year)) + "-" + str(int(month)) + "-" + str(int(day)) for year, month, day in zip(features['year'], features['month'], features['day'])] dates = [datetime.datetime.strptime(date, "%Y-%m-%d") for date in dates] # 進行畫圖操作 plt.style.use("fivethirtyeight") fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize=(10, 10)) fig.autofmt_xdate(rotation=45) ax1.plot(dates, features["temp_1"]) ax1.set_xlabel('') ax1.set_ylabel('Temperature') ax1.set_title("Previous max Temp") ax2.plot(dates, features["temp_2"]) ax2.set_xlabel('') ax2.set_ylabel('Temperature') ax2.set_title("Two day Prio max Temp") ax3.plot(dates, features["friend"]) ax3.set_xlabel('') ax3.set_ylabel('Temperature') ax3.set_title("Friend Estimate") ax4.plot(dates, features["actual"]) ax4.set_xlabel('') ax4.set_ylabel('Temperature') ax4.set_title("Max Temperature") plt.tight_layout(pad=2) plt.show() #數據格式化 獨熱編碼 features = pd.get_dummies(features) features.head(5) # 標簽 labels = np.array(features['actual']) # 在特征中去掉標簽 features= features.drop('actual', axis = 1) # 名字單獨保存一下,以備后患 feature_list = list(features.columns) # 轉換成合適的格式 features = np.array(features) #數據預處理 from sklearn import preprocessing input_features = preprocessing.StandardScaler().fit_transform(features) x=torch.tensor(input_features, dtype=torch.float) y=torch.tensor(labels, dtype=torch.float) #權重參數初始化 weights1=torch.randn((14,128), dtype=torch.float, requires_grad=True) biases1=torch.randn(128, dtype=torch.float, requires_grad=True) weights2=torch.randn((128,1), dtype=torch.float, requires_grad=True) biases2=torch.randn(1,dtype=torch.float, requires_grad=True) learning_rate=0.001 losses=[] for i in range(1000): #-------------前向傳播---------------------- #計算隱層 hidden=x.mm(weights1)+biases1 #.mm是一個矩陣乘法 #加入激活函數 hidden=torch.relu(hidden) #預測結果 predictions=hidden.mm(weights2)+biases2 #-------------------------------------------- #計算損失,均方誤差 loss=torch.mean((predictions-y)**2) losses.append(loss.data.numpy()) #打印損失值 if i%100==0: print('loss:', loss) #反向傳播計算(如何基於損失來計算w1,b1,w2,b2,使用反向傳播) loss.backward() #更新參數 weights1.data.add_(-learning_rate*weights1.grad.data) biases1.data.add_(-learning_rate*biases1.grad.data) weights2.data.add_(-learning_rate*weights2.grad.data) biases2.data.add_(-learning_rate*biases2.grad.data) #每次更新迭代后記得清空 weights1.grad.data.zero_() biases1.grad.data.zero_() weights2.grad.data.zero_() biases2.grad.data.zero_()